光学精密工程2025，Vol.33Issue(8)：1313-1326,14.DOI:10.37188/OPE.20253308.1313
目标检测与光流融合的对象级动态同步定位与地图构建方法
Object-level dynamic simultaneous localization and mapping method fusing object detection and optical flow
摘要
Abstract
Most existing visual Simultaneous Localization and Mapping(SLAM)systems assume a static environment.This assumption leads to significant degradation in positioning accuracy in dynamic scenes.To address this limitation,this paper introduced an object-level dynamic SLAM method.The method in-tegrated object detection with optical flow techniques.Object detection was used to acquire detailed seman-tic information about objects.Optical flow and object reprojection technologies were employed to distin-guish between static and dynamic objects.Feature points associated with dynamic objects were subse-quently removed.An optimal matching relationship was established between detected objects and map ob-jects.Static objects were optimized within keyframes to improve localization accuracy.A dynamic quadrat-ic surface optimization strategy was introduced.This strategy optimized dynamic quadratic surface models in the object map.It also enabled the tracking of dynamic object trajectories.Finally,the method recon-structed a dense static background.Experiments were conducted on the Bonn and TUM datasets.The re-sults demonstrate significant improvements in accuracy.Absolute pose accuracy improves by 44.3%.Rel-ative pose accuracy improves by 19.0%.These findings confirm that our method can deliver more precise and robust localization in dynamic scenes.To further validate the system's online performance,real-world dynamic scenarios were tested.The experimental results met the expected performance standards.These tests confirmed the system's reliability in practical applications.关键词
动态场景/同步定位与地图构建/光流/二次曲面/对象检测Key words
dynamic scenes/SLAM/optical flow/quadratic surface/object detection分类
计算机与自动化引用本文复制引用
李曙光,陈沁梅,史金龙,白素琴,王成根,左欣..目标检测与光流融合的对象级动态同步定位与地图构建方法[J].光学精密工程,2025,33(8):1313-1326,14.基金项目
浙江省科技计划项目(No.2024C04056(CSJ)) （No.2024C04056(CSJ）
国家自然科学基金委员会面上项目(No.51875270) （No.51875270）
中国民航大学民航智慧机场理论与系统重点实验室开放基金资助(No.SATS202207) （No.SATS202207）
